1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
|
import subprocess
import threading
import time
import csv
import argparse
import os
import sys
from datetime import datetime
import re
import fcntl
stop_event = threading.Event()
def user_input_thread():
"""A simple thread that waits for the user to press Enter and then sets the stop event."""
input("Tool is running... Press [Enter] to stop and save results.\n")
stop_event.set()
def parse_biosnoop_output(raw_data: str) -> (list, list):
"""Custom parser for biosnoop's output."""
print("Using 'biosnoop' parser...")
headers = ["TIME", "COMM", "PID", "DISK", "T", "SECTOR", "BYTES", "LAT(ms)"]
data_rows = []
lines = raw_data.strip().split('\n')
start_line = 1 if lines and lines[0].strip().startswith("TIME") else 0
for line in lines[start_line:]:
if not line.strip(): continue
parts = re.split(r'\s+', line.strip(), maxsplit=len(headers)-1)
if len(parts) == len(headers):
data_rows.append(parts)
return headers, data_rows
def parse_biotop_output(raw_data: str) -> (list, list):
"""Custom parser for biotop's output, which only processes the final screen."""
print("Using 'biotop' parser...")
headers = ["PID", "COMM", "D", "DISK", "I/O", "Kbytes", "AVGms"]
data_rows = []
last_header_index = raw_data.rfind("PID")
if last_header_index == -1: return headers, []
relevant_data = raw_data[last_header_index:]
lines = relevant_data.strip().split('\n')
for line in lines[1:]:
line = line.strip()
if not line or "Ending" in line: continue
parts = re.split(r'\s+', line, maxsplit=len(headers)-1)
if len(parts) == len(headers):
data_rows.append(parts)
return headers, data_rows
def parse_biopattern_output(raw_data: str) -> (list, list):
"""Custom parser for biopattern's output."""
print("Using 'biopattern' parser...")
headers = ["DISK", "%RND", "%SEQ", "COUNT", "KBYTES"]
data_rows = []
last_header_index = raw_data.rfind("DISK")
if last_header_index == -1: return headers, []
relevant_data = raw_data[last_header_index:]
lines = relevant_data.strip().split('\n')
for line in lines[1:]:
line = line.strip()
if not line or "Tracing" in line or "Ending" in line: continue
parts = re.split(r'\s+', line)
if len(parts) == len(headers):
data_rows.append(parts)
return headers, data_rows
def parse_histogram_output(raw_data: str, tool_name: str) -> (list, list):
"""A generic parser for histogram-based tools like biolatency and bitesize."""
print(f"Using '{tool_name}' (histogram) parser...")
if tool_name == "biolatency":
headers = ["Disk", "Latency Range", "Unit", "Count", "Distribution"]
elif tool_name == "bitesize":
headers = ["Size Range (KBytes)", "Count", "Distribution"]
else:
headers = ["Range", "Count", "Distribution"]
data_rows = []
current_disk = "all"
current_unit = "us" if " (us)" in raw_data else "ms"
lines = raw_data.strip().split('\n')
for line in lines:
line = line.strip()
if not line or "Tracing" in line or "Ending" in line: continue
disk_match = re.match(r'disk = (\S+)', line)
if disk_match:
current_disk = disk_match.group(1)
continue
hist_match = re.match(r'(\S+\s*->\s*\S+|\S+)\s*:\s*(\d+)\s*\|(.*)\|', line)
if hist_match:
groups = hist_match.groups()
rng, count, dist = groups[0].strip(), groups[1], groups[2].strip()
if tool_name == "biolatency":
data_rows.append([current_disk, rng, current_unit, count, dist])
elif tool_name == "bitesize":
data_rows.append([rng, count, dist])
return headers, data_rows
PARSERS = {
"biosnoop": parse_biosnoop_output,
"biotop": parse_biotop_output,
"biopattern": parse_biopattern_output,
"biolatency": lambda data: parse_histogram_output(data, "biolatency"),
"bitesize": lambda data: parse_histogram_output(data, "bitesize"),
}
def main():
"""The main function that orchestrates the entire process."""
parser = argparse.ArgumentParser(
description="A script to monitor system activity using bcc-tools and save the results to a CSV file.",
formatter_class=argparse.RawTextHelpFormatter,
epilog=f"""
Examples:
sudo ./monitor_and_save.py biosnoop
sudo ./monitor_and_save.py biopattern -o /tmp/logs
sudo ./monitor_and_save.py biolatency
Supported tools: {', '.join(PARSERS.keys())}
"""
)
parser.add_argument("tool", help="The name of the bcc tool to run.")
parser.add_argument("-o", "--output_dir", default=".", help="The directory to save the CSV file (default: current directory).")
args = parser.parse_args()
tool_name = args.tool
output_dir = args.output_dir
if tool_name not in PARSERS:
print(f"Error: Unsupported tool '{tool_name}'. Please choose from: {list(PARSERS.keys())}", file=sys.stderr)
sys.exit(1)
if os.geteuid() != 0:
print("Error: This script requires root privileges to run bcc-tools. Please use 'sudo'.", file=sys.stderr)
sys.exit(1)
tool_path = f"/usr/sbin/{tool_name}-bpfcc"
if not os.path.exists(tool_path):
print(f"Error: Tool '{tool_path}' not found. Please ensure bcc-tools are installed correctly.", file=sys.stderr)
sys.exit(1)
os.makedirs(output_dir, exist_ok=True)
input_thread = threading.Thread(target=user_input_thread)
input_thread.start()
command = [tool_path]
print(f"Starting: {' '.join(command)}...")
process = subprocess.Popen(
command,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
text=True,
encoding='utf-8',
errors='ignore',
preexec_fn=os.setsid
)
stdout_fd = process.stdout.fileno()
flags = fcntl.fcntl(stdout_fd, fcntl.F_GETFL)
fcntl.fcntl(stdout_fd, fcntl.F_SETFL, flags | os.O_NONBLOCK)
captured_output = ""
print("-" * 60)
while not stop_event.is_set():
try:
chunk = process.stdout.read(4096)
if chunk:
print(chunk, end='', flush=True)
captured_output += chunk
else:
if process.poll() is not None:
break
time.sleep(0.1)
except BlockingIOError:
time.sleep(0.1)
continue
except KeyboardInterrupt:
break
print("-" * 60)
print("\nStopping the tool...")
try:
os.killpg(os.getpgid(process.pid), 15)
process.wait(timeout=5)
except (ProcessLookupError, PermissionError):
pass
except subprocess.TimeoutExpired:
print("Tool did not terminate gracefully, forcing shutdown...")
os.killpg(os.getpgid(process.pid), 9)
print("Processing captured data...")
full_output = captured_output
parser_func = PARSERS[tool_name]
headers, data_rows = parser_func(full_output)
if not data_rows:
print("⚠️ Warning: No valid data was parsed. The tool may have run for too short a time.")
return
timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
output_filename = os.path.join(output_dir, f"{tool_name}_output_{timestamp}.csv")
try:
with open(output_filename, 'w', newline='', encoding='utf-8') as csvfile:
writer = csv.writer(csvfile)
writer.writerow(headers)
writer.writerows(data_rows)
print(f"✅ Success! Results saved to: {output_filename}")
except IOError as e:
print(f"❌ Error: Could not write to file {output_filename}. Reason: {e}", file=sys.stderr)
if __name__ == "__main__":
main()
|
